{"id":"184bc893-341e-4a38-b5d2-daf5ee1910cc","slug":"hf-model-manh1011-qwen2-5-vl-3b-grpo-thinking-t5cmho-10","name":"Qwen2.5-VL-3B-GRPO-Thinking","description":"Hugging Face model Manh1011/Qwen2.5-VL-3B-GRPO-Thinking. Task: image text to text. Library: transformers. 21 downloads.","capabilities":["transformers","safetensors","qwen2_5_vl","image-text-to-text","vision-language","conversational","text-generation-inference","grpo","thinking","reasoning","vi","en","dataset:lmms-lab/multimodal-open-r1-8k-verified","base_model:Qwen/Qwen2.5-VL-3B-Instruct","base_model:finetune:Qwen/Qwen2.5-VL-3B-Instruct","license:apache-2.0","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:39.530Z"}